Acquired Electronics360

Consumer Electronics

Here is the First Embedded Neural Network on a USB Stick

28 April 2016

Neural Networks are used in many applications, such as object recognition, natural speech understanding and autonomous navigation for cars. Instead of requiring engineers to program rules for machines to follow, a lot of data are processed offline in self-teaching systems. Neural networks tend to run more efficiently than traditional approaches when it comes to language comprehension, image recognition and pattern detection.

Low-power machine vision technology company, Movidius, is giving us a world’s first. The company announced the release of two products: Fathom Neural Compute Stick—the world’s first deep-learning acceleration module, and Fathom's deep-learning software framework.

Fathom Neural Compute Stick (Image Credit: Movidius) Fathom Neural Compute Stick (Image Credit: Movidius)

The tools will work together to allow powerful neural networks to be moved from the cloud into end-user devices.

The Fathom Neural Compute Stick employs an ultra-low-power Myriad 2 processor inside, and can run fully trained neural networks at under one Watt of power. It provides standard USB connectivity, so it can be connected to a range of devices and enhance their neural compute capabilities by orders of magnitude.

Once connected to your computer, the Fathom Neural Compute Stick acts as a neural network profiling and evaluation tool, which means that companies can prototype products that require AI at much faster rates.

“As a participant in the deep-learning ecosystem, I have been hoping for a long time that something like Fathom would become available,” said Dr. Yann LeCun, Founding Director of New York University Data Science Center. “The Fathom Neural Compute Stick is a compact, low-power convolutional net accelerator for embedded applications that is quite unique. As a tinkerer and builder of various robots and flying contraptions, I've been dreaming of getting my hands on something like the Fathom Neural Compute Stick for a long time. With Fathom every robot, big and small, can now have state-of-the-art vision capabilities.”

The stick allows developers to take their existing neural networks and automatically deploy a low-power optimized version to any devices that contain a Myriad 2 processor.

“It’s going to mean that very soon, consumers are going to be introduced to surprisingly smart applications and products. It means the same level of surprise and delight we saw at the beginning of the smartphone revolution—we’re going to see again with the machine intelligence revolution,” said Remi El-Ouazzane, Movidius CEO.



Powered by CR4, the Engineering Community

Discussion – 0 comments

By posting a comment you confirm that you have read and accept our Posting Rules and Terms of Use.
Engineering Newsletter Signup
Get the Engineering360
Stay up to date on:
Features the top stories, latest news, charts, insights and more on the end-to-end electronics value chain.
Advertisement
Weekly Newsletter
Get news, research, and analysis
on the Electronics industry in your
inbox every week - for FREE
Sign up for our FREE eNewsletter
Advertisement

CALENDAR OF EVENTS

Date Event Location
30 Nov-01 Dec 2017 Helsinki, Finland
23-27 Apr 2018 Oklahoma City, Oklahoma
18-22 Jun 2018 Honolulu, Hawaii
Find Free Electronics Datasheets
Advertisement